| ▲ | Baidu released ERNIE 5.5 Flash Base(ernie.baidu.com) |
| 46 points by pretext 2 hours ago | 29 comments |
| |
|
| ▲ | speedping an hour ago | parent | next [-] |
| ERNIE feels old, like BERT. They either need a rebrand or fully embrace retro-dawn-of-ML vibes |
| |
| ▲ | josh-wrale 39 minutes ago | parent | next [-] | | Bert and Ernie. Ring a bell? Sesame Steeet | |
| ▲ | lofties an hour ago | parent | prev | next [-] | | BERT models are still amazing for what they do. Even the latest JEV/KEV/SEV/BEV/REV/TREV models can't beat a well-trained BERT. | | |
| ▲ | throwaw12 41 minutes ago | parent [-] | | do you have examples of open weight BERT models from hugging face which are trained for specific use cases? |
| |
| ▲ | NSUserDefaults an hour ago | parent | prev [-] | | I'd try DONALD for sure, if I wanted to kill a project. | | |
| ▲ | ahoka an hour ago | parent | next [-] | | But they didn't give a DONALD. | |
| ▲ | yehoshuapw an hour ago | parent | prev | next [-] | | Make AI Great Again? | | |
| ▲ | selectodude an hour ago | parent [-] | | SI* | | |
| ▲ | throwaw12 39 minutes ago | parent [-] | | Trump just realised that he can't use MAGA for Making SI Great Again, probably giving an executive order to reverse SI to AI again, to be able to claim Make AI Great Again | | |
| ▲ | swingboy 28 minutes ago | parent [-] | | I am PLEASED TO ANNOUNCE that SI will be America’s 51st STATE and will be RENAMED to “American Intelligence”! Thank you for your attention to this matter! |
|
|
| |
| ▲ | locknitpicker 39 minutes ago | parent | prev [-] | | > I'd try DONALD for sure, if I wanted to kill a project. The current version is threatening to veto all my prompts. | | |
| ▲ | rob74 14 minutes ago | parent [-] | | ...and when it makes a mistake, it blames anything or anyone else but itself, or insists that what it did is perfect the way it is and that it's still the smartest model in the world? |
|
|
|
|
| ▲ | Tepix 21 minutes ago | parent | prev | next [-] |
| That's an interesting size, it will fit into 2x128GB at decent (≥4bpw) quantization. |
|
| ▲ | A_D_E_P_T 2 hours ago | parent | prev | next [-] |
| This is awesome. ERNIE seems more powerful than Qwen3.8-27B and Deepseek-v4-Flash, which AFAIK are currently the best base models... it'll be very interesting to experiment with when it hits OpenCode. Base models are also excellent for businesses who run models locally, as they can be trained in various house rules and house styles. |
| |
| ▲ | input_sh an hour ago | parent | next [-] | | They're comparing it to Deepseek-v4-Flash, not 4.1 and not the 4.1 1017 update, so essentially two versions behind the latest version of Deepseek Flash. | | |
| ▲ | Tepix 20 minutes ago | parent [-] | | DeepSeek 4.1 Flash is twice the size of this and difficult to run locally. Makes more sense to compare it to DS4F. |
| |
| ▲ | irthomasthomas an hour ago | parent | prev [-] | | Qwen3.8-27B has no base model version in the wild that I can see? | | |
|
|
| ▲ | roryirvine an hour ago | parent | prev | next [-] |
| Am I the only one to feel sad that the name means "Enhanced Representation through kNowledge IntEgration", rather than being a homage to a very famous 1950s random number generator? https://en.wikipedia.org/wiki/Premium_Bonds#ERNIE |
| |
| ▲ | jojogeo an hour ago | parent | next [-] | | For me I see ERNIE as BERT's long time friend and room mate. How do I look Ernie? ... with your eyes, Bert. | |
| ▲ | cubefox an hour ago | parent | prev [-] | | It's a homage to BERT (Bidirectional Encoder Representations from Transformers), Google's influential 2018 Transformer model that wasn't autoregressive. https://arxiv.org/abs/1810.04805v2 |
|
|
| ▲ | weijiejason119 2 hours ago | parent | prev | next [-] |
| anyone tried this? is it good? |
| |
| ▲ | spwa4 2 hours ago | parent [-] | | It's not instruction finetuned, so no, it's not good to use for anything like coding agents. |
|
|
| ▲ | haunter an hour ago | parent | prev | next [-] |
| OT dropped is the worst word in this context because it can both
mean ‘released’ or ‘terminated/ended’ Baidu dropped ERNIE 5.5 Flash Base = Baidu released a new version of their software Baidu dropped ERNIE 5.5 Flash Base = Baidu ended the support of their software |
| |
| ▲ | swiftcoder an hour ago | parent [-] | | I think in contemporary parlance this sufficiently clear. Nobody thought massdrop was where you went to buy end-of-life products. |
|
|
| ▲ | spwa4 2 hours ago | parent | prev [-] |
| TLDR: Ernie 5.5 Flash base 280B params 14B active A chunk better than Deepseek 1017, at half the parameter count, BUT it's only a base model, not finetuned to follow instructions. Strange to release a model in this state. OpenAI is also "probably" releasing new models (sources within OpenAI talking about Sol 6.2 and the like). We must be getting really close to the Qwen4 releases. |
| |
| ▲ | cubefox an hour ago | parent | next [-] | | > Strange to release a model in this state. No, they explain why they do it. | |
| ▲ | v9v an hour ago | parent | prev [-] | | I believe they compare to DSv4, not DSv4.1 1017. | | |
|
